© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 27670
    Prev
    Next
    INDEX
    Explanations

    parentheses and their corresponding closing brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    470
    +0.17
    0.9%
    190
    +0.14
    0.8%
    139
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    250
    +0.17
    0.20
    412
    +0.14
    0.15
    258
    +0.14
    0.14
    Negative Logits
    holders
    -1.63
    ños
    -1.59
    mable
    -1.49
     survives
    -1.48
    bys
    -1.47
    yel
    -1.42
    yll
    -1.36
     alive
    -1.32
    gers
    -1.32
     salv
    -1.32
    POSITIVE LOGITS
    nai
    2.03
    eness
    1.74
     myself
    1.64
    ubicin
    1.51
    iance
    1.43
    other
    1.38
    sponsored
    1.38
    isco
    1.30
     support
    1.29
    others
    1.28
    Activations Density 0.325%

    No Known Activations